BrainSegNet: A Novel Framework for Whole-Brain MRI Parcellation Enhanced by Large Models

2026-01-14

AI Summary

This work addresses the challenge of whole-brain MRI segmentation, which requires precise delineation of 95 intricate anatomical regions—a task where conventional approaches suffer from low efficiency and general-purpose foundation models lack the necessary fine-grained capability. To overcome these limitations, the authors propose BrainSegNet, a novel framework that innovatively integrates the Segment Anything Model (SAM) with a U-Net architecture. The design features a hybrid encoder, a multi-scale attention decoder, and a boundary refinement module, effectively combining skip connections with pyramid pooling mechanisms. Experimental results on the Human Connectome Project (HCP) dataset demonstrate that BrainSegNet significantly outperforms current state-of-the-art methods, achieving superior accuracy and robustness in multi-label whole-brain segmentation.

Technology Category

• Computer Vision: Segmentation
• Humans and AI: Brain-Sensing and Analysis
• Machine Learning: Deep Neural Architectures and Foundation Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Agentic search
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Whole-brain parcellation from MRI is a critical yet challenging task due to the complexity of subdividing the brain into numerous small, irregular shaped regions. Traditionally, template-registration methods were used, but recent advances have shifted to deep learning for faster workflows. While large models like the Segment Anything Model (SAM) offer transferable feature representations, they are not tailored for the high precision required in brain parcellation. To address this, we propose BrainSegNet, a novel framework that adapts SAM for accurate whole-brain parcellation into 95 regions. We enhance SAM by integrating U-Net skip connections and specialized modules into its encoder and decoder, enabling fine-grained anatomical precision. Key components include a hybrid encoder combining U-Net skip connections with SAM's transformer blocks, a multi-scale attention decoder with pyramid pooling for varying-sized structures, and a boundary refinement module to sharpen edges. Experimental results on the Human Connectome Project (HCP) dataset demonstrate that BrainSegNet outperforms several state-of-the-art methods, achieving higher accuracy and robustness in complex, multi-label parcellation.

Problem

• whole-brain parcellation
• MRI segmentation
• fine-grained anatomical precision
• multi-label parcellation
• brain region segmentation

Innovation

• BrainSegNet
• Segment Anything Model
• whole-brain parcellation
• multi-scale attention
• boundary refinement